What is broken on our Checkmk site, and has anyone acknowledged it?
Checkmk tells you what is broken on your own monitoring site. Memtro reads the services in WARN, CRIT or UNKNOWN across the site or on one host, with their output, last check, hard or soft state, and whether each is acknowledged or in downtime. It also reads every service on one host with a count per state, a single service, and the site's version. When asked and granted, it can acknowledge a host or service problem, remove an acknowledgement, and start a service discovery on a host. A discovery only creates pending changes, which somebody must still activate in Setup.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Checkmk tool, reads what it needs, and answers with the source cited.
These tools change something in Checkmk. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Once Checkmk is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
What is critical in Checkmk right now?
Which problems on db01 are unacknowledged?
Show me every service on web02, worst first.
When was the backup service on db01 last checked?
Acknowledge the disk space problem on db01 with a note that Tom is on it.
Dan Fletcher, an infrastructure engineer at Acme Ltd, asked which Checkmk problems were still unacknowledged. Memtro listed the CRIT and WARN services with their output and last check, and flagged the ones already in downtime so he could skip them.
Maya Okafor, who runs operations at Northwind, asked Memtro to acknowledge the CRIT disk check on db01 while a new volume was ordered. Memtro acknowledged it with her comment and no notification, so it stopped alerting as unhandled and its contacts were not messaged.
The teams that lean on Checkmk most, a question each of them asks, and what they connect beside it.
A record in Checkmk is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
UptimeRobot
Honeycomb
Cronitor
FireHydrant
StatusCake
GlitchTip
GLPI
Langfuse
LibreNMS
NetBox
Snipe-IT
Woodpecker CI
Zabbix
LangSmith
Helicone
GrowthBook
Drata
Intruder
GitGuardian
Secureframe
ilert
JumpCloud
ConfigCat
Split
Aikido Security
Astronomer
Comet Opik
CrowdStrike Falcon
Detectify
Domotz
LambdaTest
LangWatch
LlamaCloud
Logz.io
Lunary
NinjaOne
Northflank
Portkey
PromptLayer
PRTG Network Monitor
Raygun
Retell AI
Runpod
Shodan
Spike.sh
Squadcast
Tenable
UpGuard
Uptime.com
Vanta
Zenduty
Cortex
WorkOS
Kandji
Automox
Huntress
SimpleMDM
Healthchecks.io
Rapid7 InsightVM
ZenhubIn Checkmk, open Setup → Users → Users and create an automation user. Give it a role that can see all hosts and services, and acknowledge problems if you want that.
In Memtro, open Connections → Checkmk and paste the Host (name only, no https://), the Site from the web address, the Automation user and its Automation secret.
Set the API version to 1.0 if the site runs Checkmk 2.4 or earlier, and the port if the web interface is not on 443. An administrator grants the acknowledge and discovery actions to the teams that may use them.
Ask what is critical in Checkmk right now, or which problems on db01 are unacknowledged.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Checkmk tools are the same everywhere.
Only when you ask, and only what it has been granted: acknowledge a host problem; acknowledge a service problem; remove an acknowledgement from a host or service; start a service discovery (refresh) on a host. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
Host, site, automation user and automation secret. In Checkmk, open Setup → Users → Users and create an automation user. Give it a role that can see all hosts and services, and acknowledge problems if you want that.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time
